Fix occupancy calculation functions in ROCclr path

The hipOccupancyMaxPotentialBlockSize API is meant to return the
number of threads for the highest-occupancy workgroup, and the number
of those workgroups. It was previously calculating the number of
maximum-sized workgroups that would fit on a single CU. This is
a mixture of the API we wanted (to calculate max potential block size)
and the MaxBlocksPerMultiprocessor function.

This patch fixes it up so that the internal occupancy calculation
function works for two uses: the traditional function that calculates
the maximum blocks per multiprocessor when a user passes in a fixed
block size (used for hipMaxBlocksPerMultiprocessor style functions)
and a function that calculates the size of a block that would lead
to maximum occupancy, and how many blocks of that size would be
needed to fill the whole GPU (for hipOccupancyMaxPotentialBlockSize
style functions).

This also updates the occupancy calculation function to prepare for
gfx10, which does not have SGPR-based occupancy limits.

Change-Id: Ie007b3f9d5ebc4e166b50a3a051498af35650f35

rocclr/hip_module.cpp

@@ -392,11 +392,12 @@ hipError_t ihipModuleLaunchKernel(hipFunction_t f,
       return hipErrorLaunchFailure;
     }
     int num_blocks = 0;
-    int num_grids = 0;
+    int max_blocks_per_grid = 0;
+    int best_block_size = 0;
     int block_size = blockDimX * blockDimY * blockDimZ;
     hip_impl::ihipOccupancyMaxActiveBlocksPerMultiprocessor(
-      &num_blocks, &num_grids, device, f, block_size, sharedMemBytes, true);
-    if (((gridDimX * gridDimY * gridDimZ) / block_size) > unsigned(num_grids)) {
+      &num_blocks, &max_blocks_per_grid, &best_block_size, device, f, block_size, sharedMemBytes, true);
+    if (((gridDimX * gridDimY * gridDimZ) / block_size) > unsigned(max_blocks_per_grid)) {
       return hipErrorCooperativeLaunchTooLarge;
     }
   }